create_npc_mnemonsCreate NPC mnemons (individual people). role is an optional free-text role or occupation. Use affiliationEntryIds to name the factions each NPC belongs to; the server projects them into MEMBER relationships. For a faction, guild or cult use create_faction_mnemons. Players may not call this — GM/co-GM only.
| Name | Required | Description | Default |
|---|---|---|---|
| items | Yes | ||
| campaignId | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| results | Yes |
Changes observed during successful MCP inspections.
Input schema / properties / items / items / properties / affiliationEntryIds / descriptionPrevious value: -"INDIVIDUAL only: factions this person belongs to."New value: +"Factions this person belongs to (Faction entryIds or titles)."Input schema / properties / items / items / properties / memberNpcEntryIdsRemoved value: -{
- "description": "FACTION only: members of this faction (NPC entryIds or titles).",
- "items": {
- "type": "string"
- },
- "type": "array"
-}Input schema / properties / items / items / properties / npcTypeRemoved value: -{
- "description": "Required: FACTION (organization) or INDIVIDUAL (person).",
- "enum": [
- "FACTION",
- "INDIVIDUAL"
- ],
- "type": "string"
-}Input schema / properties / items / items / properties / roleAdded value: +{
+ "description": "Free-text role or occupation, e.g. \"innkeeper\", \"captain of the guard\".",
+ "type": "string"
+}Input schema / properties / items / items / requiredPrevious value: -[
- "title",
- "markdown",
- "npcType"
-]New value: +[
+ "title",
+ "markdown"
+]Input schema / properties / items / items / properties / blocksRemoved value: -{
- "description": "Initial content blocks (at least one).",
- "items": {
- "additionalProperties": false,
- "description": "A single content block. Image blocks need assetId OR (data + mimeType).",
- "properties": {
- "assetId": {
- "description": "Image block: pre-uploaded campaign asset id.",
- "type": "string"
- },
- "caption": {
- "description": "Image block caption.",
- "type": "string"
- },
- "checked": {
- "description": "Todo-block checked state.",
- "type": "boolean"
- },
- "content": {
- "description": "HTML text content for text-type blocks. Use <b>/<i>/<u>/<a>/<br>/<img> — NOT Markdown.",
- "type": "string"
- },
- "data": {
- "description": "Image block: inline base64 data (decoded server-side, max 5MB).",
- "type": "string"
- },
- "filename": {
- "description": "Image block filename hint.",
- "type": "string"
- },
- "language": {
- "description": "Code-block language hint.",
- "type": "string"
- },
- "mimeType": {
- "description": "Image block mime type — required when 'data' is set.",
- "type": "string"
- },
- "type": {
- "description": "Block type.",
- "enum": [
- "paragraph",
- "heading1",
- "heading2",
- "bullet_list",
- "numbered_list",
- "todo",
- "quote",
- "code",
- "callout",
- "divider",
- "image"
- ],
- "type": "string"
- }
- },
- "required": [
- "type"
- ],
- "type": "object"
- },
- "minItems": 1,
- "type": "array"
-}Input schema / properties / items / items / properties / markdownAdded value: +{
+ "description": "Body content as Markdown. Mentions: @[label](mnemon:<entryId>). Images:  — upload the asset first.",
+ "minLength": 1,
+ "type": "string"
+}Input schema / properties / items / items / requiredPrevious value: -[
- "title",
- "blocks",
- "npcType"
-]New value: +[
+ "title",
+ "markdown",
+ "npcType"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=false and destructiveHint=false, so the write/safety profile is already covered. The description adds genuinely non-derived behavior: affiliationEntryIds cause the server to project MEMBER relationships, and the GM-only authorization requirement. It doesn't mention the 50-item batch cap or what happens on partial failure, keeping it short of a 5.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four compact sentences, no filler, with the core purpose first and the sibling exclusion and auth rule trailing. Every sentence carries decision-relevant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
An output schema exists, so return values need no explanation, and the description covers purpose, alternative, side effects, and auth. It omits the batch-size limit and the meaning/effect of visibility, which is a minor but real omission for a bulk-create tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Reported schema coverage is 0%, so the description must compensate, and it only explains two fields: role as free-text occupation and affiliationEntryIds as accepted entryIds/titles. campaignId, markdown mention syntax, visibility, and sheetId receive no added meaning, leaving real gaps.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Create NPC mnemons (individual people)') and immediately scopes it against the obvious sibling by naming create_faction_mnemons for groups. An agent can distinguish this from the other create_*_mnemons tools without opening a schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly routes the agent: use this for individual people, use create_faction_mnemons for factions/guilds/cults. It also states the access condition ('Players may not call this — GM/co-GM only'), which prevents a whole class of failed calls.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.